Perception of vocoded speech in domestic dogs by Amritha Mallikarjun, Emily Shroads, Rochelle S. Newman

Subjects: Get full text

Software Simulation in GSM Environment and Hardware Implementation of Improved Multi-band Excitation Vocoder by Kuang Jingming Li Feng Liu Botao (Electronic Engineering Department, Beijing Institute of Technology, Beijing 100081)

Get full text

Speech Perception as a Function of the Number of Channels and Channel Interaction in Cochlear Implant Simulation by Mustafa YUKSEL, Sultan Nur KAYA

“…Results: In the first experiment, participants scored 57.93%, 80.97%, 83.59%, 91.03%, and 95.45% under 8, 12, 16, and 22-channel vocoder and non-vocoder conditions, respectively. …”
Get full text

Tibetan–Chinese speech-to-speech translation based on discrete units by Zairan Gong, Xiaona Xu, Yue Zhao

“…Leveraging HuBERT model to extract discrete units of target speech, we develop a speech-to-unit translation (S2UT) model using an encoder-decoder architecture which subsequently generates speech output through a unit-based vocoder. By employing SSL and utilizing discrete representations as training targets, our approach effectively captures linguistic differences, facilitating direct translation between the two languages. …”
Get full text

Time Series Classification of Raw Voice Waveforms for Parkinson's Disease Detection Using Generative Adversarial Network-Driven Data Augmentation by Marta Rey-Paredes, Carlos J. Perez, Alfonso Mateos-Caballero

“…This article also implements a data augmentation solution. Big Vocoder Slicing Adversarial Network (BigVSAN) is used to generate synthetic voice data that mimics the characteristics of real patients and healthy subjects. …”
Get full text

GOLF: A Singing Voice Synthesiser with Glottal Flow Wavetables and LPC Filters by Chin-Yun Yu, György Fazekas

“…We show it is competitive with state-of-the-art singing voice vocoders, requiring fewer synthesis parameters and less memory to train, and runs an order of magnitude faster for inference. …”
Get full text

End-to-End Speech Synthesis for Tibetan Multidialect by Xiaona Xu, Li Yang, Yue Zhao, Hui Wang

“…Thirdly, two dialect-specific WaveNet vocoders are combined with the feature prediction network, which synthesizes the Mel spectrum of Lhasa-Ü-Tsang and Amdo pastoral dialect into time-domain waveform, respectively. …”
Get full text